DeepViewRT
Inference Engine

™

AVAILABLE NOW! 

Best In Class Performance and Unprecedented Portability

The DeepViewRT runtime inference engine provides developers with the freedom to quickly deploy ML models to a broad selection of embedded devices and compute architectures without sacrificing flexibility or performance.

​

Select a proven public model from DeepView model zoo, create or convert your own model with NXP's eIQ portal and compare performance tradeoffs between quantized and floating point under real-world runtime conditions.

Lastest DeepViewRT Benchmarks

164,300+

100,000,000+

Real world inferences (and counting)

The DeepViewRT engine has been highly optimized for runtime size and performance across a long list of the most popular embedded processors, architectures and standard x86 class devices - this means you can run public, custom and proprietary ML models anywhere the DeepViewRT engine is supported. 

​

Best of all, it's FREE for development and production.

Benefits of the DeepViewRT production-ready engine
 

• Tested & documented for quick out-of-the-box deployment

• Examples and tutorials to save you time getting started

• Field proven to avoid surprises when you ship your products

• Lifecycle management for stability, longevity & compatibility

• Professional support if you need it

​

Runtime environments 
 

• Embedded: Linux, Android, Azure, FreeRTOS and bare metal

• Desktop: Linux and Windows​​

Lastest DeepViewRT Benchmarks

Processor Types & Compute Architectures:

​

• Microcontrollers (MCPUs): Arm Cortex M7

• Application Processors(CPUs): Arm Cortex A35, 53, 72  

• Graphics Processing Units (GPUs): OpenVx

• Neural Processing Units (NPU's): VeriSilicon and Ethos*

• Desktop: x86 (development & validation) 

Model deployment formats:
 

• Floating point for full precision accuracy

• Fixed point for optimal size and efficiency

Questions?